Recherche avancée
Autres articles (94)
-
MediaSPIP 0.1 Beta version
25 avril 2011, parMediaSPIP 0.1 beta is the first version of MediaSPIP proclaimed as "usable".
The zip file provided here only contains the sources of MediaSPIP in its standalone version.
To get a working installation, you must manually install all-software dependencies on the server.
If you want to use this archive for an installation in "farm mode", you will also need to proceed to other manual (...) -
Multilang : améliorer l’interface pour les blocs multilingues
18 février 2011, parMultilang est un plugin supplémentaire qui n’est pas activé par défaut lors de l’initialisation de MediaSPIP.
Après son activation, une préconfiguration est mise en place automatiquement par MediaSPIP init permettant à la nouvelle fonctionnalité d’être automatiquement opérationnelle. Il n’est donc pas obligatoire de passer par une étape de configuration pour cela. -
HTML5 audio and video support
13 avril 2011, parMediaSPIP uses HTML5 video and audio tags to play multimedia files, taking advantage of the latest W3C innovations supported by modern browsers.
The MediaSPIP player used has been created specifically for MediaSPIP and can be easily adapted to fit in with a specific theme.
For older browsers the Flowplayer flash fallback is used.
MediaSPIP allows for media playback on major mobile platforms with the above (...)
Sur d’autres sites (11053)
-
libavformat/libavcodec providing invalid container header
14 décembre 2017, par seanr8I’m using libavcodec to encode a stream to h264 and libavformat to store it in an mp4. The resulting container has an invalid header that can be played in VLC, but not any other player.
I’ve found that using the mp4 container and the "mpeg4" codec produces a valid mp4 file, but using libx265 (HEVC) or the libx264 codec produces invalid mp4s.
I can use
ffmpeg -i invalid.mp4 -vcodec copy valid.mp4and I get a file of almost the exact same size, but in a valid container.Examples of these files are here : Broken file and
Repaied file [use the download links in the upper right to examine]I used a hex editor to see the differences in the headers of the two files and the invalid one is 1 byte smaller than the valid one.
The code I’m using to open the container and codec and to write the header is here :
AVOutputFormat *container_format;
AVFormatContext *container_format_context;
AVStream *video_stream;
int ret;
/* allocate the output media context */
avformat_alloc_output_context2(&container_format_context, NULL, NULL, out_file);
if (!container_format_context) {
log(INFO, "Unable to determine container format from filename, exiting\n");
exit(1);
}
else {
log(INFO, "Using container %s\n", container_format_context->oformat->name);
}
if (!container_format_context) {
log(ERROR, "Could not build container format context. Encoding failed.");
exit(1);
}
container_format = container_format_context->oformat;
/* Pull codec based on name */
AVCodec* codec = avcodec_find_encoder_by_name(codec_name);
if (codec == NULL) {
log(ERROR, "Failed to locate codec \"%s\".",
codec_name);
exit(1);
}
/* create stream */
video_stream = NULL;
video_stream = avformat_new_stream(container_format_context, codec);
if (!video_stream) {
log(ERROR, "Could not allocate encoder stream. Cannot continue.\n");
exit(1);
}
video_stream->id = container_format_context->nb_streams - 1;
video_stream->time_base = video_stream->codec->time_base = (AVRational) { 1, 25};
av_dump_format(container_format_context, 0, out_file, 1);
/* Retrieve encoding context */
AVCodecContext* avcodec_context = video_stream->codec;
if (avcodec_context == NULL) {
log(ERROR, "Failed to allocate context for "
"codec \"%s\".", codec_name);
exit(1);
}
/* Init context with encoding parameters */
avcodec_context->bit_rate = bitrate;
avcodec_context->width = width;
avcodec_context->height = height;
avcodec_context->gop_size = 10;
avcodec_context->max_b_frames = 1;
avcodec_context->qmax = 31;
avcodec_context->qmin = 2;
avcodec_context->pix_fmt = AV_PIX_FMT_YUV420P;
av_dump_format(container_format_context, 0, out_file, 1);
/* Open codec for use */
if (avcodec_open2(avcodec_context, codec, NULL) < 0) {
log(ERROR, "Failed to open codec \"%s\".", codec_name);
exit(1);
}
/* Allocate corresponding frame */
AVFrame* frame = av_frame_alloc();
if (frame == NULL) {
exit(1);
}
/* Copy necessary data for frame from avcodec_context */
frame->format = avcodec_context->pix_fmt;
frame->width = avcodec_context->width;
frame->height = avcodec_context->height;
/* Allocate actual backing data for frame */
if (av_image_alloc(frame->data, frame->linesize, frame->width,
frame->height, frame->format, 32) < 0) {
exit(1);
}
/* open the output file, if the container needs it */
if (!(container_format->flags & AVFMT_NOFILE)) {
ret = avio_open(&container_format_context->pb, out_file, AVIO_FLAG_WRITE);
if (ret < 0) {
log(ERROR, "Error occurred while opening output file: %s\n",
av_err2str(ret));
exit(1);
}
}
/* write the stream header, if needed */
ret = avformat_write_header(container_format_context, NULL);
if (ret < 0) {
log(ERROR, "Error occurred while writing output file header: %s\n",
av_err2str(ret));
}The code to encode a frame is here :
/* Init video packet */
AVPacket packet;
av_init_packet(&packet);
/* Request that encoder allocate data for packet */
packet.data = NULL;
packet.size = 0;
/* Write frame to video */
int got_data;
if (avcodec_encode_video2(avcontext, &packet, frame, &got_data) < 0) {
log(WARNING, "Error encoding frame #%" PRId64,
video_struct->next_pts);
return -1;
}
/* Write corresponding data to file */
if (got_data) {
if (packet.pts != AV_NOPTS_VALUE) {
packet.pts = av_rescale_q(packet.pts, video_struct->output_stream->codec->time_base, video_struct->output_stream->time_base);
}
if (packet.dts != AV_NOPTS_VALUE) {
packet.dts = av_rescale_q(packet.dts, video_struct->output_stream->codec->time_base, video_struct->output_stream->time_base);
}
write_packet(video_struct, &packet, packet.size);
av_packet_unref(&packet);
}And the code to write the packet to the video stream :
static int write_packet(video_struct* video, void* data, int size) {
int ret;
/* use AVStream is not null, otherwise write to output fd */
AVPacket *pkt = (AVPacket*) data;
pkt->stream_index = video->output_stream->index;
ret = av_interleaved_write_frame(video->container_format_context, pkt);
if (ret != 0) {
return -1;
}
/* Data was written successfully */
return ret;
} -
C++ ffmpeg - export to wav error : Invalid PCM packet, data has size 2 but at least a size of 4 was expected
9 septembre 2024, par Chris PC++ code :


AudioSegment AudioSegment::from_file(const std::string& file_path, const std::string& format, const std::string& codec,
 const std::map& parameters, int start_second, int duration) {

 avformat_network_init();
 av_log_set_level(AV_LOG_ERROR); // Adjust logging level as needed

 AVFormatContext* format_ctx = nullptr;
 if (avformat_open_input(&format_ctx, file_path.c_str(), nullptr, nullptr) != 0) {
 std::cerr << "Error: Could not open audio file." << std::endl;
 return AudioSegment(); // Return an empty AudioSegment on failure
 }

 if (avformat_find_stream_info(format_ctx, nullptr) < 0) {
 std::cerr << "Error: Could not find stream information." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 int audio_stream_index = -1;
 for (unsigned int i = 0; i < format_ctx->nb_streams; i++) {
 if (format_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
 audio_stream_index = i;
 break;
 }
 }

 if (audio_stream_index == -1) {
 std::cerr << "Error: Could not find audio stream." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 AVCodecParameters* codec_par = format_ctx->streams[audio_stream_index]->codecpar;
 const AVCodec* my_codec = avcodec_find_decoder(codec_par->codec_id);
 AVCodecContext* codec_ctx = avcodec_alloc_context3(my_codec);

 if (!codec_ctx) {
 std::cerr << "Error: Could not allocate codec context." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 if (avcodec_parameters_to_context(codec_ctx, codec_par) < 0) {
 std::cerr << "Error: Could not initialize codec context." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 if (avcodec_open2(codec_ctx, my_codec, nullptr) < 0) {
 std::cerr << "Error: Could not open codec." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 SwrContext* swr_ctx = swr_alloc();
 if (!swr_ctx) {
 std::cerr << "Error: Could not allocate SwrContext." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }
 codec_ctx->sample_rate = 44100;
 // Set up resampling context to convert to S16 format with 2 bytes per sample
 av_opt_set_chlayout(swr_ctx, "in_chlayout", &codec_ctx->ch_layout, 0);
 av_opt_set_int(swr_ctx, "in_sample_rate", codec_ctx->sample_rate, 0);
 av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", codec_ctx->sample_fmt, 0);

 AVChannelLayout dst_ch_layout;
 av_channel_layout_copy(&dst_ch_layout, &codec_ctx->ch_layout);
 av_channel_layout_uninit(&dst_ch_layout);
 av_channel_layout_default(&dst_ch_layout, 2);

 av_opt_set_chlayout(swr_ctx, "out_chlayout", &dst_ch_layout, 0);
 av_opt_set_int(swr_ctx, "out_sample_rate", codec_ctx->sample_rate, 0); // Match input sample rate
 av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", AV_SAMPLE_FMT_S16, 0); // Force S16 format

 if (swr_init(swr_ctx) < 0) {
 std::cerr << "Error: Failed to initialize the resampling context" << std::endl;
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 AVPacket packet;
 AVFrame* frame = av_frame_alloc();
 if (!frame) {
 std::cerr << "Error: Could not allocate frame." << std::endl;
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 std::vector<char> output;
 while (av_read_frame(format_ctx, &packet) >= 0) {
 if (packet.stream_index == audio_stream_index) {
 if (avcodec_send_packet(codec_ctx, &packet) == 0) {
 while (avcodec_receive_frame(codec_ctx, frame) == 0) {
 if (frame->pts != AV_NOPTS_VALUE) {
 frame->pts = av_rescale_q(frame->pts, codec_ctx->time_base, format_ctx->streams[audio_stream_index]->time_base);
 }

 uint8_t* output_buffer;
 int output_samples = av_rescale_rnd(
 swr_get_delay(swr_ctx, codec_ctx->sample_rate) + frame->nb_samples,
 codec_ctx->sample_rate, codec_ctx->sample_rate, AV_ROUND_UP);

 int output_buffer_size = av_samples_get_buffer_size(
 nullptr, 2, output_samples, AV_SAMPLE_FMT_S16, 1);

 output_buffer = (uint8_t*)av_malloc(output_buffer_size);

 if (output_buffer) {
 memset(output_buffer, 0, output_buffer_size); // Zero padding to avoid random noise
 int converted_samples = swr_convert(swr_ctx, &output_buffer, output_samples,
 (const uint8_t**)frame->extended_data, frame->nb_samples);

 if (converted_samples >= 0) {
 output.insert(output.end(), output_buffer, output_buffer + output_buffer_size);
 }
 else {
 std::cerr << "Error: Failed to convert audio samples." << std::endl;
 }
 // Make sure output_buffer is valid before freeing
 if (output_buffer != nullptr) {
 av_free(output_buffer);
 output_buffer = nullptr; // Prevent double-free
 }
 }
 else {
 std::cerr << "Error: Could not allocate output buffer." << std::endl;
 }
 }
 }
 else {
 std::cerr << "Error: Failed to send packet to codec context." << std::endl;
 }
 }
 av_packet_unref(&packet);
 }

 int frame_width = av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * 2; // Use 2 bytes per sample and 2 channels

 std::map metadata = {
 {"sample_width", 2}, // S16 format has 2 bytes per sample
 {"frame_rate", codec_ctx->sample_rate}, // Use the input sample rate
 {"channels", 2}, // Assuming stereo output
 {"frame_width", frame_width}
 };

 av_frame_free(&frame);
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);

 return AudioSegment(static_cast<const>(output.data()), output.size(), metadata);
}

std::ofstream AudioSegment::export_segment_to_wav_file(const std::string& out_f) {
 std::cout << this->get_channels() << std::endl;
 av_log_set_level(AV_LOG_ERROR);
 AVCodecContext* codec_ctx = nullptr;
 AVFormatContext* format_ctx = nullptr;
 AVStream* stream = nullptr;
 AVFrame* frame = nullptr;
 AVPacket* pkt = nullptr;
 int ret;

 // Initialize format context for WAV
 if (avformat_alloc_output_context2(&format_ctx, nullptr, "wav", out_f.c_str()) < 0) {
 throw std::runtime_error("Could not allocate format context.");
 }

 // Find encoder for PCM
 const AVCodec* codec_ptr = avcodec_find_encoder(AV_CODEC_ID_PCM_S16LE);
 if (!codec_ptr) {
 throw std::runtime_error("PCM encoder not found.");
 }

 // Add stream
 stream = avformat_new_stream(format_ctx, codec_ptr);
 if (!stream) {
 throw std::runtime_error("Failed to create new stream.");
 }

 // Allocate codec context
 codec_ctx = avcodec_alloc_context3(codec_ptr);
 if (!codec_ctx) {
 throw std::runtime_error("Could not allocate audio codec context.");
 }

 // Set codec parameters for PCM
 codec_ctx->bit_rate = 128000; // Bitrate
 codec_ctx->sample_rate = this->get_frame_rate(); // Use correct sample rate
 codec_ctx->ch_layout.nb_channels = this->get_channels(); // Set the correct channel count

 // Set the channel layout: stereo or mono
 if (this->get_channels() == 2) {
 av_channel_layout_default(&codec_ctx->ch_layout, 2); // Stereo layout
 }
 else {
 av_channel_layout_default(&codec_ctx->ch_layout, 1); // Mono layout
 }

 codec_ctx->sample_fmt = AV_SAMPLE_FMT_S16; // PCM 16-bit format

 // Open codec
 if (avcodec_open2(codec_ctx, codec_ptr, nullptr) < 0) {
 throw std::runtime_error("Could not open codec.");
 }

 // Set codec parameters to the stream
 if (avcodec_parameters_from_context(stream->codecpar, codec_ctx) < 0) {
 throw std::runtime_error("Could not initialize stream codec parameters.");
 }

 // Open output file
 std::ofstream out_file(out_f, std::ios::binary);
 if (!out_file) {
 throw std::runtime_error("Failed to open output file.");
 }

 if (!(format_ctx->oformat->flags & AVFMT_NOFILE)) {
 if (avio_open(&format_ctx->pb, out_f.c_str(), AVIO_FLAG_WRITE) < 0) {
 throw std::runtime_error("Could not open output file.");
 }
 }

 // Write file header
 if (avformat_write_header(format_ctx, nullptr) < 0) {
 throw std::runtime_error("Error occurred when writing file header.");
 }

 // Initialize packet
 pkt = av_packet_alloc();
 if (!pkt) {
 throw std::runtime_error("Could not allocate AVPacket.");
 }

 // Initialize frame
 frame = av_frame_alloc();
 if (!frame) {
 throw std::runtime_error("Could not allocate AVFrame.");
 }

 // Set the frame properties
 frame->format = codec_ctx->sample_fmt;
 frame->ch_layout = codec_ctx->ch_layout;

 // Number of audio samples available in the data buffer
 int total_samples = data_.size() / (av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * codec_ctx->ch_layout.nb_channels);
 int samples_read = 0;

 // Set the number of samples per frame dynamically based on the input data
 while (samples_read < total_samples) {
 // Determine how many samples to read in this iteration (don't exceed the total sample count)
 int num_samples = std::min(codec_ctx->frame_size, total_samples - samples_read);
 if (num_samples == 0) {
 num_samples = 1024;
 codec_ctx->frame_size = 1024;
 }
 // Ensure num_samples is not zero
 if (num_samples <= 0) {
 throw std::runtime_error("Invalid number of samples in frame.");
 }

 // Set the number of samples in the frame
 frame->nb_samples = num_samples;

 // Allocate the frame buffer based on the number of samples
 ret = av_frame_get_buffer(frame, 0);
 if (ret < 0) {
 std::cerr << "Error allocating frame buffer: " << ret << std::endl;
 throw std::runtime_error("Could not allocate audio data buffers.");
 }

 // Copy the audio data into the frame's buffer (interleaving if necessary)
 /*if (codec_ctx->ch_layout.nb_channels == 2) {
 // If stereo, interleave planar data into packed format
 for (int i = 0; i < num_samples; ++i) {
 ((int16_t*)frame->data[0])[2 * i] = ((int16_t*)data_.data())[i]; // Left channel
 ((int16_t*)frame->data[0])[2 * i + 1] = ((int16_t*)data_.data())[total_samples + i]; // Right channel
 }
 }
 else {
 // For mono or packed data, directly copy the samples
 std::memcpy(frame->data[0], data_.data() + samples_read * av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * codec_ctx->ch_layout.nb_channels,
 num_samples * av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * codec_ctx->ch_layout.nb_channels);
 }
 */
 std::memcpy(frame->data[0], data_.data() + samples_read * av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * codec_ctx->ch_layout.nb_channels,
 num_samples * av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * codec_ctx->ch_layout.nb_channels);

 // Send the frame for encoding
 ret = avcodec_send_frame(codec_ctx, frame);
 if (ret < 0) {
 std::cerr << "Error sending frame for encoding: " << ret << std::endl;
 throw std::runtime_error("Error sending frame for encoding.");
 }

 // Receive and write encoded packets
 while (ret >= 0) {
 ret = avcodec_receive_packet(codec_ctx, pkt);
 if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
 break;
 }
 else if (ret < 0) {
 throw std::runtime_error("Error during encoding.");
 }

 out_file.write(reinterpret_cast(pkt->data), pkt->size);
 av_packet_unref(pkt);
 }

 samples_read += num_samples;
 }

 // Flush the encoder
 if (avcodec_send_frame(codec_ctx, nullptr) < 0) {
 throw std::runtime_error("Error flushing the encoder.");
 }

 while (avcodec_receive_packet(codec_ctx, pkt) >= 0) {
 out_file.write(reinterpret_cast(pkt->data), pkt->size);
 av_packet_unref(pkt);
 }

 // Write file trailer
 av_write_trailer(format_ctx);

 // Cleanup
 av_frame_free(&frame);
 av_packet_free(&pkt);
 avcodec_free_context(&codec_ctx);

 if (!(format_ctx->oformat->flags & AVFMT_NOFILE)) {
 avio_closep(&format_ctx->pb);
 }
 avformat_free_context(format_ctx);

 out_file.close();
 return out_file;
}

</const></char>

Run code :


#include "audio_segment.h"
#include "effects.h"
#include "playback.h"
#include "cppaudioop.h"
#include "exceptions.h"
#include "generators.h"
#include "silence.h"
#include "utils.h"

#include <iostream>
#include <filesystem>

using namespace cppdub;

int main() {
 try {
 // Load the source audio file
 AudioSegment seg_1 = AudioSegment::from_file("../data/test10.mp3");
 std::string out_file_name = "ah-ah-ah.wav";

 // Export the audio segment to a new file with specified settings
 //seg_1.export_segment(out_file_name, "mp3");
 seg_1.export_segment_to_wav_file(out_file_name);


 // Optionally play the audio segment to verify
 // play(seg_1);

 // Load the exported audio file
 AudioSegment seg_2 = AudioSegment::from_file(out_file_name);

 // Play segments
 //play(seg_1);
 play(seg_2);
 }
 catch (const std::exception& e) {
 std::cerr << "An error occurred: " << e.what() << std::endl;
 }

 return 0;
}
</filesystem></iostream>

Error in second call of from_file function :


[pcm_s16le @ 000002d82ca5bfc0] Invalid PCM packet, data has size 2 but at least a size of 4 was expected


The process continue, i call hear the seg_2 with play(seg_2) call, but i can't directly play seg_2 export wav file (from windows explorer).


I had a guess that error may be because packed vs plannar formats missmatch but i am not quit sure. Maybe a swr_convert is necessary.


-
C++ ffmpeg lib version 7.0 - noice in exported audio
2 septembre 2024, par Chris PI want to make a C++ lib named cppdub which will mimic the python module pydub.


One main function is to export the AudioSegment to a file with a specific format (example : mp3).


The code is :


AudioSegment AudioSegment::from_file(const std::string& file_path, const std::string& format, const std::string& codec,
 const std::map& parameters, int start_second, int duration) {

 avformat_network_init();
 av_log_set_level(AV_LOG_ERROR); // Adjust logging level as needed

 AVFormatContext* format_ctx = nullptr;
 if (avformat_open_input(&format_ctx, file_path.c_str(), nullptr, nullptr) != 0) {
 std::cerr << "Error: Could not open audio file." << std::endl;
 return AudioSegment(); // Return an empty AudioSegment on failure
 }

 if (avformat_find_stream_info(format_ctx, nullptr) < 0) {
 std::cerr << "Error: Could not find stream information." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 int audio_stream_index = -1;
 for (unsigned int i = 0; i < format_ctx->nb_streams; i++) {
 if (format_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
 audio_stream_index = i;
 break;
 }
 }

 if (audio_stream_index == -1) {
 std::cerr << "Error: Could not find audio stream." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 AVCodecParameters* codec_par = format_ctx->streams[audio_stream_index]->codecpar;
 const AVCodec* my_codec = avcodec_find_decoder(codec_par->codec_id);
 AVCodecContext* codec_ctx = avcodec_alloc_context3(my_codec);

 if (avcodec_parameters_to_context(codec_ctx, codec_par) < 0) {
 std::cerr << "Error: Could not initialize codec context." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 if (avcodec_open2(codec_ctx, my_codec, nullptr) < 0) {
 std::cerr << "Error: Could not open codec." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 SwrContext* swr_ctx = swr_alloc();
 if (!swr_ctx) {
 std::cerr << "Error: Could not allocate SwrContext." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 av_opt_set_chlayout(swr_ctx, "in_chlayout", &codec_ctx->ch_layout, 0);
 av_opt_set_int(swr_ctx, "in_sample_rate", codec_ctx->sample_rate, 0);
 av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", codec_ctx->sample_fmt, 0);

 AVChannelLayout dst_ch_layout;
 av_channel_layout_copy(&dst_ch_layout, &codec_ctx->ch_layout);
 av_channel_layout_uninit(&dst_ch_layout);
 av_channel_layout_default(&dst_ch_layout, 2);

 av_opt_set_chlayout(swr_ctx, "out_chlayout", &dst_ch_layout, 0);
 av_opt_set_int(swr_ctx, "out_sample_rate", 48000, 0);
 av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", AV_SAMPLE_FMT_S16, 0);

 if (swr_init(swr_ctx) < 0) {
 std::cerr << "Error: Failed to initialize the resampling context" << std::endl;
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 AVPacket packet;
 AVFrame* frame = av_frame_alloc();
 if (!frame) {
 std::cerr << "Error: Could not allocate frame." << std::endl;
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 std::vector<char> output;
 while (av_read_frame(format_ctx, &packet) >= 0) {
 if (packet.stream_index == audio_stream_index) {
 if (avcodec_send_packet(codec_ctx, &packet) == 0) {
 while (avcodec_receive_frame(codec_ctx, frame) == 0) {
 if (frame->pts != AV_NOPTS_VALUE) {
 frame->pts = av_rescale_q(frame->pts, codec_ctx->time_base, format_ctx->streams[audio_stream_index]->time_base);
 }

 uint8_t* output_buffer;
 int output_samples = av_rescale_rnd(
 swr_get_delay(swr_ctx, codec_ctx->sample_rate) + frame->nb_samples,
 48000, codec_ctx->sample_rate, AV_ROUND_UP);

 int output_buffer_size = av_samples_get_buffer_size(
 nullptr, 2, output_samples, AV_SAMPLE_FMT_S16, 1);

 output_buffer = (uint8_t*)av_malloc(output_buffer_size);

 if (output_buffer) {
 memset(output_buffer, 0, output_buffer_size); // Zero padding to avoid random noise
 int converted_samples = swr_convert(swr_ctx, &output_buffer, output_samples,
 (const uint8_t**)frame->extended_data, frame->nb_samples);

 if (converted_samples >= 0) {
 output.insert(output.end(), output_buffer, output_buffer + output_buffer_size);
 }
 else {
 std::cerr << "Error: Failed to convert audio samples." << std::endl;
 }

 av_free(output_buffer);
 }
 else {
 std::cerr << "Error: Could not allocate output buffer." << std::endl;
 }
 }
 }
 else {
 std::cerr << "Error: Failed to send packet to codec context." << std::endl;
 }
 }
 av_packet_unref(&packet);
 }

 av_frame_free(&frame);
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);

 std::map metadata = {
 {"sample_width", 2},
 {"frame_rate", 48000},
 {"channels", 2},
 {"frame_width", 4}
 };

 return AudioSegment(static_cast<const>(output.data()), output.size(), metadata);
}


std::ofstream AudioSegment::export_segment(std::string& out_f,
 const std::string& format,
 const std::string& codec,
 const std::string& bitrate,
 const std::vector& parameters,
 const std::map& tags,
 const std::string& id3v2_version,
 const std::string& cover) {
 av_log_set_level(AV_LOG_DEBUG);
 AVCodecContext* codec_ctx = nullptr;
 AVFormatContext* format_ctx = nullptr;
 AVStream* stream = nullptr;
 AVFrame* frame = nullptr;
 AVPacket* pkt = nullptr;
 int ret;

 // Open output file
 std::ofstream out_file(out_f, std::ios::binary);
 if (!out_file) {
 throw std::runtime_error("Failed to open output file.");
 }

 // Initialize format context
 avformat_alloc_output_context2(&format_ctx, nullptr, format.c_str(), out_f.c_str());
 if (!format_ctx) {
 throw std::runtime_error("Could not allocate format context.");
 }

 // Find encoder
 const AVCodec* codec_ptr = avcodec_find_encoder_by_name(codec.c_str());
 if (!codec_ptr) {
 throw std::runtime_error("Codec not found.");
 }

 // Add stream
 stream = avformat_new_stream(format_ctx, codec_ptr);
 if (!stream) {
 throw std::runtime_error("Failed to create new stream.");
 }

 // Allocate codec context
 codec_ctx = avcodec_alloc_context3(codec_ptr);
 if (!codec_ctx) {
 throw std::runtime_error("Could not allocate audio codec context.");
 }

 // Set codec parameters
 codec_ctx->bit_rate = std::stoi(bitrate);
 codec_ctx->sample_fmt = codec_ptr->sample_fmts ? codec_ptr->sample_fmts[0] : AV_SAMPLE_FMT_FLTP;
 codec_ctx->sample_rate = frame_rate_;
 codec_ctx->ch_layout.nb_channels = this->get_channels();
 AVChannelLayout ch_layout_1;
 av_channel_layout_uninit(&ch_layout_1);
 av_channel_layout_default(&ch_layout_1, this->get_channels());
 codec_ctx->ch_layout = ch_layout_1;

 // Open codec
 ret = avcodec_open2(codec_ctx, codec_ptr, nullptr);
 if (ret < 0) {
 throw std::runtime_error("Could not open codec.");
 }

 // Initialize packet
 pkt = av_packet_alloc();
 if (!pkt) {
 throw std::runtime_error("Could not allocate AVPacket.");
 }

 // Initialize frame
 frame = av_frame_alloc();
 if (!frame) {
 throw std::runtime_error("Could not allocate AVFrame.");
 }

 frame->nb_samples = codec_ctx->frame_size;
 frame->format = codec_ctx->sample_fmt;
 frame->ch_layout = codec_ctx->ch_layout;
 frame->sample_rate = codec_ctx->sample_rate;

 // Allocate data buffer
 ret = av_frame_get_buffer(frame, 0);
 if (ret < 0) {
 throw std::runtime_error("Could not allocate audio data buffers.");
 }

 // Encode frames
 int samples_read = 0;
 while (samples_read < data_.size()) {
 ret = av_frame_make_writable(frame);
 if (ret < 0) {
 throw std::runtime_error("Frame not writable.");
 }

 // Determine the number of samples to copy into the frame
 int frame_size = std::min<int>(codec_ctx->frame_size, (data_.size() - samples_read) / frame_width_);
 int buffer_size = frame_size * frame_width_;

 // Clear the frame data to avoid artifacts from previous data
 std::memset(frame->data[0], 0, codec_ctx->frame_size * frame_width_);

 // Copy the actual audio data into the frame
 std::memcpy(frame->data[0], data_.data() + samples_read, buffer_size);
 samples_read += buffer_size;

 // If the frame is partially filled, pad the remaining part with zeros
 if (frame_size < codec_ctx->frame_size) {
 std::memset(frame->data[0] + buffer_size, 0, (codec_ctx->frame_size - frame_size) * frame_width_);
 }

 // Send the frame for encoding
 ret = avcodec_send_frame(codec_ctx, frame);
 if (ret < 0) {
 throw std::runtime_error("Error sending frame for encoding.");
 }

 // Receive and write packets
 while (ret >= 0) {
 ret = avcodec_receive_packet(codec_ctx, pkt);
 if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
 break;
 }
 else if (ret < 0) {
 throw std::runtime_error("Error encoding frame.");
 }

 out_file.write(reinterpret_cast(pkt->data), pkt->size);
 av_packet_unref(pkt);
 }
 }

 // **Explicitly flush the encoder**
 ret = avcodec_send_frame(codec_ctx, nullptr);
 if (ret < 0) {
 throw std::runtime_error("Error flushing the encoder.");
 }

 // Receive and write remaining packets after flushing
 while (ret >= 0) {
 ret = avcodec_receive_packet(codec_ctx, pkt);
 if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
 break;
 }
 else if (ret < 0) {
 throw std::runtime_error("Error encoding frame during flush.");
 }

 out_file.write(reinterpret_cast(pkt->data), pkt->size);
 av_packet_unref(pkt);
 }

 // Cleanup
 av_frame_free(&frame);
 av_packet_free(&pkt);
 avcodec_free_context(&codec_ctx);
 avformat_free_context(format_ctx);

 return out_file;
}
</int></const></char>

I have no run time error but i see this message in console :


[libmp3lame @ 000002d26b239ac0] Trying to remove 47 more samples than there are in the queue


I can play the exported mp3 file but there is background noise.


Syndiquer tout le site
